Semi-supervised Bayesian Deep Multi-modal Emotion Recognition

TL;DR

This paper introduces a semi-supervised Bayesian deep multi-modal emotion recognition model that effectively leverages both labeled and unlabeled multi-modal data, overcoming data scarcity and modality limitations.

Contribution

It presents a novel multi-view deep generative model with a Gaussian mixture prior, extending to semi-supervised learning for emotion recognition from multiple modalities.

Findings

Outperforms existing methods on two real datasets

Learns modality weights automatically

Robust and flexible in handling limited labeled data

Abstract

In emotion recognition, it is difficult to recognize human's emotional states using just a single modality. Besides, the annotation of physiological emotional data is particularly expensive. These two aspects make the building of effective emotion recognition model challenging. In this paper, we first build a multi-view deep generative model to simulate the generative process of multi-modality emotional data. By imposing a mixture of Gaussians assumption on the posterior approximation of the latent variables, our model can learn the shared deep representation from multiple modalities. To solve the labeled-data-scarcity problem, we further extend our multi-view model to semi-supervised learning scenario by casting the semi-supervised classification problem as a specialized missing data imputation task. Our semi-supervised multi-view deep generative framework can leverage both labeled and unlabeled data from multiple modalities, where the weight factor for each modality can be learned automatically. Compared with previous emotion recognition methods, our method is more robust and flexible. The experiments conducted on two real multi-modal emotion datasets have demonstrated the superiority of our framework over a number of competitors.